Beating the World’s Best at Super Smash Bros. with Deep Reinforcement Learning

Re:Beating the World’s Best at Super Smash Bros. with Deep R... by RoboTeddy on Wednesday February 22, 2017 @07:42PM (#13710669)

I heard that the DeepMind Starcraft project intends to limit their AI's APM (actions per minute) down to something human-like.

[ Parent | on HN ]

Re:Beating the World’s Best at Super Smash Bros. with Deep R... by wapz on Wednesday February 22, 2017 @08:23PM (#13710850)

I read that too but I hope they know the difference between APM and EPM. Pros spam APM that they could never do real actions on but their EPM is considerably lower (if the bots make actions based on pros APM they will have an insurmountable advantage).

[ Parent | on HN ]

Re:Beating the World’s Best at Super Smash Bros. with Deep R... by placeybordeaux on Wednesday February 22, 2017 @09:08PM (#13711059)

Pros spam APM to keep warm, during battles or production macros they will frequently have a high EPM as well.

[ Parent | on HN ]

Re:Beating the World’s Best at Super Smash Bros. with Deep R... by leereeves on Thursday February 23, 2017 @06:33AM (#13713102)

There's also accuracy.

Unlike a human, a bot will always "click" exactly where it intends to.

[ Parent | on HN ]